English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, representation learning for text and speech has successfullyimproved many language related tasks. However, all existing methods suffer fromtwo limitations: (a) they only learn from one input modality, while a unifiedrepresentation for both speech and text is needed by tasks such as end-to-endspeech translation, and as a result,(b) they can not exploit variouslarge-scale text and speech data and their performance is limited by thescarcity of parallel speech translation data.To address these problems, wepropose a Fused Acoustic and Text Masked Language Model (FAT-MLM) which jointlylearns a unified representation for both acoustic and text input from varioustypes of corpora including parallel data for speech recognition and machinetranslation, and even pure speech and text data. Within this cross-modalrepresentation learning framework, we further present an end-to-end model forFused Acoustic and Text Speech Translation (FAT-ST). Experiments on threetranslation directions show that by fine-tuning from FAT-MLM, our proposedspeech translation models substantially improve translation quality by up to+5.9 BLEU.

Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation